Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jeonje/claude-plugins/verification-workflownpx skills add JeonJe/claude-plugins --skill verification-workflowgit clone --depth 1 https://github.com/JeonJe/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jeonje/claude-plugins/verification-workflow)<a href="https://agentmods.dev/skills/jeonje/claude-plugins/verification-workflow"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/verification-workflow.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00091 | $0.02307 |
| Opus 5 | $0.00046 | $0.01154 |
| Sonnet 5 | $0.00018 | $0.00461 |
| Haiku 4.5 | $0.00009 | $0.00231 |
Grade A, and why
verification-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Workflow
A risk-gated pipeline from requirement to commit. The review/verification stages can be implemented by any agent roster — role names below (researcher, architect, reviewer, executor) are roles, not specific agents. Simple one-off work needs only self-verification (lint/type/test) plus the commit gate.
Full flow
요구사항 입력
↓
[모호함 체크] → 해당 시 사용자에게 질문
↓
[복잡도 판단] → 단순(1-2파일): 계획 직행 / 복잡(3+파일): Research 단계 진입
↓
★ Research (복잡 작업 필수) — 대상 영역 분석 → research.md → 사용자 확인
↓
★ 계획 — 계획 출력 템플릿 준수, 유사 기존 구현 참조 필수 → plan.md
↓
★ Annotation Cycle (복잡 작업 필수, 1-3회)
→ 사용자 주석/피드백 → 계획 갱신 → "아직 구현하지 마라"
↓
★ 계획 검증 — 결함·누락 / 보안 / 정책 정합성 관점의 독립 리뷰
↓
[공유 모듈 변경?] → YES: 영향 모듈 식별
↓
구현 (외과적·최소 diff·컨벤션 준수)
↓
테스트 단계 (references/testing.md) — 요구사항 기반·예외/경계·회귀·커버리지
↓
린트/타입/테스트 (스택별 fresh 출력)
↓
★ 코드 검증 — 독립 리뷰. CERTAIN 지적은 자동 수정 / QUESTION은 사용자 확인
↓
[E2E 필요 시] 브라우저/실환경 검증 (액션 후 스크린샷 증거)
↓
커밋 전 검증 체크리스트 (아래) → Commit
↓
[검증 실패] → 자동 수정 루프 (아래)
Research 단계 (복잡 작업 필수)
트리거: 3개+ 파일 변경 예상, 또는 기존 아키텍처 이해가 필요한 작업
- 대상 코드를 깊이 분석 (관련 클래스, 의존성, 호출 흐름)
- 분석 결과를
docs/{key}/research.md등 프로젝트 문서 위치에 기록: 현재 구조 요약 / 데이터 흐름 / 제약 조건 / 변경 영향 범위 - 사용자에게 research.md 검토 요청 → 잘못된 이해를 사전 차단
- 사용자 승인 후에만 계획 단계로 진행
핵심: 잘못된 리서치는 이후 모든 단계를 망친다. 가장 비용이 큰 실패를 여기서 차단. 스킵 조건: 단순 버그 수정, 1-2파일 변경, 사용자가 "skip research" 명시
계획 출력 템플릿 (필수 준수)
## 1. 변경 파일 목록 — path + 변경 이유 한줄
## 2. 참조한 기존 구현 — path + 이 패턴을 따르는 이유
## 3. 핵심 코드 스니펫 — 주요 시그니처/핵심 로직 스케치
## 4. 대안 및 트레이드오프 — 선택 vs 대안 (최소 1개), 각각 장단점 (기록 구조: references/design-decisions.md)
## 5. 리스크 — 회귀 가능성, 성능 영향, 마이그레이션 여부
## 6. 예상 소요과 컷라인 — Phase별 구현/테스트 예상 + 근거(참조 구현 크기·파일 수·미지수),
## 시간 초과 시 자를 순서 (동작 우선 → 기본 기능 → 심화)
참조 구현 패턴: 계획 작성 전 기존 코드에서 유사 구현을 먼저 검색한다 — 동일 도메인 유사 기능 → 동일 패턴의 다른 모듈 → 기존 설계 문서. 기존 패턴과 다르게 구현하면 반드시 이유를 트레이드오프 섹션에 기록.
Annotation Cycle (복잡 작업 필수)
트리거: 3개+ 파일 변경, 아키텍처 결정 포함, 새로운 패턴 도입
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 142 lines · 91 tokens per session scan A c971d59fc867
verification-workflow is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 2,307 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
execution-grounded-review
Execution-grounded review: run tests first, trace each acceptance criterion to execution evidence. Use when verifying an implementation meets spec.
multi-model-delegation
Multi-model design consults via PAL (kimi, glm, gemini, gpt). Use when asking other models to brainstorm a design or reconciling their split answers.
blueprint-work-order
Create a work-order for isolated subagent execution, optionally linked to a GitHub issue. Use when breaking a PRP into delegatable tasks or spawning from an issue.
document-detection
Detect PRD/ADR/PRP opportunities in conversations and prompt for document creation. Use when the user discusses feature requirements, tech trade-offs, or implementation plans.
ticket-drafting-guidelines
What/Why/How prose structure and neutral, positive register for issues, PR descriptions, and tickets. Use when wording a ticket body, tightening prose, or applying house tone.
config-sync
Config sync across FVH repos: extract, diff, propagate tooling improvements. Use when syncing workflows or configs across multiple repos.